.png){kind=icon}
Return
Weakly Supervised Pixel-Level Annotation with Visual Interpretability
.png){kind=icon}
OA
AI
DOI：10.1007/978-3-032-08317-3_19.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Medical image annotation is essential for diagnosing diseases, yet manual annotation is time-consuming, costly, and prone to variability among experts. To address these challenges, we propose an automated explainable annotation system that integrates ensemble learning, visual explainability, and uncertainty quantification. Our approach combines three pre-trained deep learning models-ResNet50, EfficientNet, and DenseNet-enhanced with XGrad-CAM for visual explanations and Monte Carlo Dropout for uncertainty quantification. This ensemble mimics the consensus of multiple radiologists by intersecting saliency maps from models that agree on the diagnosis while uncertain predictions are flagged for human review. We evaluated our system using the TBX11K medical imaging dataset and a Fire segmentation dataset, demonstrating its robustness across different domains. Experimental results show that our method outperforms baseline models, achieving 93.04% accuracy on TBX11K and 96.4% accuracy on the Fire dataset. Moreover, our model produces precise pixel-level annotations despite being trained with only image-level labels, achieving Intersection over Union IoU scores of 36.07% and 64.7%, respectively. By enhancing the accuracy and interpretability of image annotations, our approach offers a reliable and transparent solution for medical diagnostics and other image analysis tasks.
Keywords:
Medical Image Annotation
Image Segmentation
Uncertainty Quantification
Ensemble Learning
Explainable Artificial Intelligence
Journal
E
IF:
0
Papers:
20
Citations:
0
Organization
Cited Papers
Early smoke detection of forest wildfire video using deep belief network.png)
2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)
2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)IF0
PREAI
ShareSaveShifting to machine supervision: annotation-efficient semi and self-supervised learning for automatic medical image segmentation and classificationSCIENTIFIC REPORTS
OAAI
SCIENTIFIC REPORTSIF3.9
OAAIShareSaveA review of uncertainty quantification in deep learning: Techniques, applications and challengesINFORMATION FUSIONOAAI
INFORMATION FUSIONIF15.5
OAAIShareSave
View more